Adam (Adaptive Moment Estimation) is one of the most widely used optimization algorithms for training deep neural…

Stochastic Gradient Descent (SGD) is a variant of the gradient descent optimization algorithm that updates model parameters…

Backpropagation (short for backward propagation of errors) is the foundational algorithm for training deep neural networks. It computes the gradient…

Gradient Descent is a fundamental optimization algorithm used to minimize the loss function of a machine learning model. It…

Batch Normalization Batch Normalization (BN) is a widely used deep learning technique that standardizes the inputs to…

Dropout is a regularization technique for deep neural networks that prevents overfitting by randomly “dropping out” (setting to zero)…

Transfer Learning Transfer Learning is a machine learning technique that enables a model trained on a source task to…

Fine-tuning is a transfer learning technique in machine learning where a pre-trained model—a model trained on a large,…

Policy Gradient is a class of reinforcement learning (RL) algorithms that directly optimize a policy function \(\pi_\theta(a|s)\)—a probability distribution over actions a given…

Actor-Critic is a hybrid reinforcement learning (RL) algorithm that combines the strengths of value-based methods (e.g., Q-Learning, SARSA) and policy-based…